The agent iteratively applies prioritized SEO fixes to the codebase, requiring human approval for each change, until the AI Readiness score reaches a target or the iteration cap is hit.
The agent connects to the Are You Found by AI? MCP server to retrieve the current visibility scores and the prioritized fix plan. It classifies fixes into in-repo changes (like JSON-LD) and external actions. For in-repo changes, it applies the code modifications, presents the diff to the human for approval, and deploys upon consent. After each approved change, it triggers a re-measurement to check progress. The loop continues until the target score is reached, the score stops improving, or the maximum iteration count is exceeded. The agent must verify the existence of a protected-pages.txt file to ensure critical pages are not edited.
- Category: Software development
- Effect: Changes data in your accounts
- MCP servers: Are You Found by AI? MCP (https://koskamo.com/explore/are-you-found-by-ai-mcp)
- Source: Connect your AI and let it work the plan | Are you found by AI? (https://areyoufoundbyai.com/guides/ai-loop)
- Source quote: "Connected to your coding agent, it turns the latest saved report into a working cycle: your agent reads your prioritised fix plan from the latest deep scan, applies the fixes that live in your repository, shows you the diff, deploys once you approve, triggers a re-measure, and reads the new score."
- Playbook page: https://koskamo.com/explore/use-cases/automate-ai-visibility-fixes-via-mcp-loop
Prompt: Run the found-by-ai loop. Target readiness 75. Max 3 iterations.